becomevocal

Like the "building blocks" mentality vs. "factory from scratch" mentality. Because... that's just how the real world works and if we are modeling intelligence off ourselves then why wouldn't that be the right approach?

Appreciate the feedback and support so far!

Wanted to add, in terms of extensibility, we've really tried to make the key parts of the UX hookable. Most of what you see on this page like tool / reasoning calls, voice, loaders, approvals, etc are completely replaceable in a few lines of plain JS: https://www.persona-chat.dev/advanced.html

It means you can do interesting things like go straight to OpenAI or Elevenlabs voice for read-aloud while streaming the main chat from your framework.

I'd like to improve the shareability of what's created in the ecosystem, but we're not quite there yet.

If you have ideas for more hooks or extensions you'd like to see, we're very much in listening mode.

IMO there's a lot more we can do around hooking into the DOM directly, with more efficient data formats over the wire, before we absolutely need WASM

We'd like to experiment more with this but haven't got their yet. Just some internal prototyping

Thanks! Definitely interested in the game overlay use case.

My gut says you'll need want to hook into custom render functions and theme config to map to your game styles, since it's going to look very different than the standard OOTB options.

The best file to use as a starting reference is here: https://github.com/runtypelabs/persona/blob/main/packages/wi...

If you run into anything, GH issues are welcome!

Appreciate it. And thank you for the work on WebMCP!

For everyone passing by, Alex created https://docs.mcp-b.ai/ and we use two of his libraries to enable WebMCP more cleanly. We found MCP-B after we built our own

It's interesting how experimental web tech vs. frameworks are. Kind of flipped once React and Next.js took off. Now we get to see what the browser can do again. Find the balance that works for each case

Note we actually use React / Vite and Next with Persona across a few of our products. It's nice in our case because the agent specific state (including event debug stream if you turn that on) doesn't need to interact with the main app at all. Keeps updates to agent UX from blowing up other parts of the app

Appreciate the quick take! Sounds like a keeper to me. I think the Opus and Fable design (that I saw for a short while) have gotten stale

Yeah wasn’t there a report recently on how local models after energy costs didn’t weren’t actually more efficient to complete the same task?

I find I there is anxiety either direction but have more engaging days when I am chasing something deeply.

First thought was "only 30 tasks" however the findings map to what I've seen personally: code review consumes majority of tokens

Feels like the active discovery going on is trying to understand what is computer vs what is AI, for every product.

Agents help a ton with the discovery, but the act of building a product needs a deeper level of thought and validation to make it actually better than what came before. So IMO what you see is people still learning what needs to be understood and crafted first hand to make a product better (including economics)

We’ll get there if more of us try

Hopefully we can blend those two options together so it’s not a choice.

Personally I find being able lean on our heavily documented standards in /review gives me back time to dive into what I want to craft next.

Same with scheduling repetitive tasks an agent can do for me well once instructed well. I am freed up to do something else I want to focus actively on because I like it and want it to be great.

Now stress about OKRs and OKRS in general… that’s a different issue

At this point you have to use more than one to get a complete picture, which I’m doing now. Mainly because: 1) some are not always up to date (started on helicone but felt a lag on price updates) 2) they don’t return every model / provider I want (https://ai-gateway.vercel.sh/v1/models has rich data but is a subset, so I combine with helicone)

I always hope for the best when someone has a new list because of this. I want a de facto source!

Made me think and smile a bit

Also I think I need to build a chicken selfie system now...

It’s an expensive hobby on top of server / service costs to run the site?

Source: myself through wife which is maxed on chickens and has her own site with no ads

Simplifying here… sounds like essentially the split between (great) product managers and engineers

We need both! Hurrah

Thank you, David. One last Sega! for ya

Have been in font picking mode recently so this was a relevant enough distraction. Excellent read!

An opportunity to provide more accessible compute for non AI tasks via new methods of utilizing GPUS?

I have 2 (CC and Codex) running within most coding sessions, however can have up to 5 if I'm trying to test out new models or tools.

For complex features and architecture shifts I like to send proposals back between agents to see if their research and opinion shifts anything.

Claude has a better realtime feel when I am in implementation mode and Codex is where I send long running research tasks or feature updates I want to review when I get up in the morning.

I'd like to test out the git worktrees method but will probably pick something outside of core product to test it (like building a set of examples)

Make it a bit more personal? I have dropped Bill and Ted references in code because it makes me happy to see it. :D

For a few years, many many years ago, I helped build the sites for wowtattoos.com and redchapterclothing.com which uses the artwork of Mark Palmer. He's the real deal! Awesome person too

Back in 2008-ish the site could generate ambigrams for you too. It was powered by an algo that pieced together a large set of hand drawn glyphs. PHP at it's best :D

https://web.archive.org/web/20080730222127/http://www.wowtat...

> Generative AI gives us incredible first drafts to work with, but few people want to put in the additional effort it requires to make work that people love

and

> So make your stuff stand out. It doesn't have to be "better." It just has to be different.

equals... craft?

Isn't that what has always mattered a great deal

I found that too, so I updated to putting limited comments at the beginning of core files that: - Describe what the file contains (e.g. endpoints for x with their route names) - Links to docs that are also in the repo (e.g. bruno files for those endpoints)

The core agent files links out to architectural and product decisions as well (i have a /docs folder for them)

This works better for me and I can get a good result when asking to make sure docs are updated whenever changes are made

Installed the app about an hour ago and have been using it as I’m on the go. Working well so far!

Going to try to build a sizable feature while doing chores to fully test it. So, thank you so much?

Very cool product! We got into chickens a few years ago and it’s taken over our life in a good way. Sounds like we’re in a similar boat as tomcam :)

I remember the first time my wife saw your coop, she said “that is what I wanted to build”, so you probably have some product market fit going on. We had already built our run at that time, however now she thinks a good supplemental product idea is a feeder with a camera. Like Petcube combined with the Grandpa’s Feeders product. She would definitely be up to chat about her chicken keeping needs and all the ideas that come with it. Her details are on her blog: tropicalchicki.com

Note for other HN peeps: If you really like cats and nature you probably will like chicken keeping! They have lots of personality and communicate in more ways than we are typically taught.

On the article, I wonder if people commonly see their first chickens in trees on islands. It’s a common thing in PR, which also has a lot of wild chickens roaming. Vieques, the smaller sister island off the east coast of PR, kind of celebrates this. Lots of chicken murals, themed gifts, names of beaches, etc

Interesting tidbit about a music video his future wife, Katherine Anna Kang, animated that used the Quake engine in the Feb 7, 2003 plan.

In the Waiting Line - Zero 7: https://www.youtube.com/watch?v=Cq336zk2cZk

Great viz!

Are you adding printers as you find them? Are open source projects OK, as long as they can be bought already assembled?

I ask because I know a team here in Austin / Houston that seems like the should be on the list: https://www.kickstarter.com/projects/re3d/open-gigabot-an-op...

I'm not sure why you experienced that but on my end I've received great support from the Mixpanel team. In fact I remember one case in particular where we were aliasing our users wrong and a team member there got on a call at 1am to resolve it.

Mixpanel is one of the few pieces of software I've been excited to pay for. Hate to see them get a bad rap.

It seems like there may be certain start-ups being targeted that aren't a perfect fit for the pricing structure. If you are B2B SaaS the price is well worth it.